Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions indicating relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.20
    aylor
    -0.16
    capacity
    -0.15
    agli
    -0.15
    и
    -0.15
     Rune
    -0.15
    CELER
    -0.14
    oron
    -0.14
    urrence
    -0.14
    pose
    -0.14
    POSITIVE LOGITS
    lä
    0.18
    LOUR
    0.17
    太éĥİ
    0.17
    warts
    0.15
    erosis
    0.15
    ]âĢı
    0.14
     centr
    0.14
    699
    0.14
    _skb
    0.14
    xAE
    0.14
    Act Density 0.052%

    No Known Activations